TWI734050B - Vehicle recognition method and system using the same, object recognition method and system using the same - Google Patents

Abstract

A vehicle recognition method and a system using the same, an object recognition method and a system using the same are provided. The vehicle recognition method includes (S1000) obtaining a first image data of a vehicle in a first location by an image obtaining device; (S3000) determining whether the first image data is a vehicle image or not by a processing module; (S5000) generating a recognition result by the processing module in accordance with the first image data when the first image data is a vehicle image; (S2000) obtaining a vehicle data of the vehicle in the first location by a data obtaining device; (S4000) determining whether the recognition result matches the vehicle data or not by the processing module; (S6000) generating a confirmation signal by the processing module when the recognition result matches the vehicle data.

Description

Vehicle identification method and system and object identification method and system

The invention relates to a vehicle identification method and system and an object identification method and system.

In the traditional manual toll collection method, it takes considerable time to collect fees, change or sell or collect the number of tickets, so the toll station area has always been the bottleneck of the expressway, and thus reduces the overall speed of the expressway. In order to improve the above phenomenon, an electronic toll collection system using advanced communication and information technology was developed.

One of the current electronic automatic charging methods is to use specific short-distance communication technology to identify, use microwave or radio frequency tags to detect deductions, which require passers-by to install equipment or tags, and the sensing effect is easily affected by the external environment and is unstable .

Another common electronic automatic toll collection method is to use image license plate recognition. This method does not require passersby to install equipment or tags. However, in addition to the location of the camera, light source, weather, license plate contamination and other factors, the image license plate recognition is based on the license plate The efficiency and accuracy of image data acquisition have a more obvious impact on it. For example, the image triggered by a bird does not contain the license plate content, which cannot be correctly identified and must be manually eliminated.

The main purpose of the present invention is to provide a vehicle identification method and system with better accuracy.

Another object of the present invention is to provide an object recognition method and system with better accuracy.

The vehicle identification method of the present invention includes the following steps: (S1000) Obtain the first image data of the vehicle at the first position by the image acquisition device; (S3000) Identify the first image data by the processing module Whether the image data is a vehicle image; (S5000) When the first image data is a vehicle image, the processing module generates a recognition result based on the first image data; (S2000) The data acquisition device acquires the vehicle data of the vehicle at the first position; (S2000) S4000) The processing module compares whether the recognition result matches the vehicle data; (S6000) When the recognition result matches the vehicle data, the processing module generates a confirmation signal.

In the embodiment of the present invention, the step (S3000) includes the following steps: (S3100) the processing module compares the first image data with the vehicle contour data; (S3300) when the ratio of the first image data to the vehicle contour data If the results match, the processing module determines that the first image data is a vehicle image.

In the embodiment of the present invention, the vehicle identification method further includes the following steps before step (S1000): (S0511) the first position is sensed by the motion sensing module; (S0512) when the motion sensing module detects To the action, proceed to step (S1000).

The vehicle identification system of the present invention includes an image acquisition device, a data acquisition device, and a processing module. The image acquisition device is used to acquire the first image data of the vehicle at the first position. The data acquisition device is used to acquire vehicle data of the vehicle at the first position. The processing module is in communication connection with the image acquisition device and the data acquisition device for distinguishing whether the first image data is a vehicle image and whether the comparison and recognition result matches the vehicle data. When the first image data is a vehicle image, the processing module generates a recognition result according to the first image data. When the comparison result between the first image data and the vehicle profile data is consistent, the processing module determines that the first image data is a vehicle image.

In an embodiment of the present invention, the vehicle identification system further includes a motion sensing module in communication with the processing module for motion sensing on the first position.

The object recognition method of the present invention includes the following steps: (T1000) Obtain the first image data of the object at the first position by the image acquisition device; (T3000) Generate the category recognition result according to the first image data by the processing module; (T2000) The data acquisition device acquires the object data of the object at the first location, where the object data includes category data; (T4000) The processing module compares whether the category recognition result matches the category data; (T6000) When the category recognition result matches the category data, A confirmation signal is generated by the processing module.

In the embodiment of the present invention, the step (T3000) includes the following steps: (T3100) the processing module compares the first image data with the category profile data; (T3300) when the first image data and the category profile data are The comparison result of the object outline data matches, and the processing module generates Category recognition result.

In the embodiment of the present invention, the step (T1000) further includes the following steps: (T0511) the first position is sensed by the motion sensing module; (T0512) when the motion sensing module senses the motion, perform the step (T1000).

The object recognition system of the present invention includes an image acquisition device, a data acquisition device, and a processing module. The image acquisition device is used to acquire the first image data of the object at the first position. The data acquisition device is used to acquire the object data of the object at the first position, where the object data includes category data. The processing module is in communication connection with the image acquisition device and the data acquisition device for generating a category recognition result based on the first image data and comparing whether the category recognition result matches the category data. When the category recognition result matches the category data, the processing module generates a confirmation signal.

In an embodiment of the present invention, the object recognition system further includes a motion sensing module in communication with the processing module for motion sensing on the first position.

100‧‧‧Image capture device

110‧‧‧Image capture device

200: data acquisition device

210: Data acquisition device

300: Processing module

310: Processing module

400: Motion sensing module

410: Motion sensing module

900: Vehicle Identification System

910: Object Recognition System

S0511: Step

S0512: Step

S1000: steps

S2000: steps

S3000: steps

S3100: steps

S3300: steps

S4000: steps

S5000: steps

S6000: steps

T0511: Steps

T0512: Steps

T1000: steps

T2000: steps

T3000: steps

T3100: steps

T3300: steps

T4000: steps

T5000: steps

T6000: steps

Fig. 1A is a schematic flow diagram of an embodiment of the vehicle identification method of the present invention; Fig. 1B is a schematic flow diagram of different embodiments of the vehicle identification method of the present invention; Fig. 2 is a schematic flow diagram of different embodiments of the vehicle identification method of the present invention; Fig. 4 is a schematic diagram of an embodiment of the vehicle recognition system of the present invention; Fig. 5 is a schematic diagram of different embodiments of the vehicle recognition system of the present invention; Fig. 6A is a schematic diagram of an embodiment of the object recognition method of the present invention; 6B is a schematic diagram of the flow of different embodiments of the object recognition method of the present invention; FIG. 7 is a schematic diagram of the flow of different embodiments of the object recognition method of the present invention; FIG. 8 is a schematic diagram of the flow of different embodiments of the object recognition method of the present invention; FIG. 9 is the present invention A schematic diagram of an embodiment of the object recognition system; FIG. 10 is a schematic diagram of different embodiments of the object recognition system of the present invention.

The vehicle identification method and system of the present invention are preferably used in an electronic toll road system, but it is not limited thereto. For example, it can be used in controlled areas or parking lots.

As shown in the embodiment shown in FIG. 1A, the vehicle identification method of the present invention includes, for example, the following step.

In step S1000, the first image data of the vehicle at the first position is acquired by the image acquisition device. Specifically, a digital camera is used as the image acquisition device, and the vehicle is photographed as the first image data. In different embodiments, a digital camera may also be used to record the vehicle, and then the vehicle in the recorded image may be captured as the first image data. Among them, the first location is a highway toll location. In a preferred embodiment, the image acquisition device is set at the first location, and acquires the first image data passing through the location as one of the basis for calculating the toll fee.

In step S3000, the processing module distinguishes whether the first image data is a vehicle image. Specifically, the processing module contains data processing functions, which can be, for example, directly installed in the chipset of the image acquisition device or connected with the image acquisition device through the Internet, wired telephone, mobile phone, data cable, microwave, radio, etc. The computer or server to which the communication is connected. Among them, the communication connection generally refers to the connection that can achieve signal transmission through the Internet, wired phones, mobile phones, data cables, microwaves, and radio. The first image data can be sent to the processing module by the image acquisition device. Furthermore, the processing module uses artificial intelligence to perform various condition judgments to distinguish whether the first image data is a vehicle image.

Furthermore, as shown in FIG. 1B, in one embodiment, step S3000 includes the following steps.

In step S3100, the processing module compares the first image data with the vehicle profile data. In step S3300, when the comparison result between the first image data and the vehicle profile data is consistent, the processing module determines that the first image data is a vehicle image. Among them, the vehicle profile data generally refers to the general outline of the vehicle's appearance, which belongs to all those that can be roughly regarded as a vehicle. The vehicle profile data can be pre-stored and recorded in the processing module, or stored in an external storage medium for the processing module to connect and read. The so-called match between the first image data and the vehicle contour data includes the first image data and the vehicle contour data having the same characteristics. For example, they all have the characteristics of the water tank cover at the front of the vehicle, the headlights on both sides of the water tank cover, the license plate and so on at the same time. In other words, if the first image data acquired by the image acquisition device is a pedestrian image, the processing module will not determine that the first image data is a vehicle image because the appearance contour of the pedestrian does not have the same or similar characteristics as the vehicle contour data.

In step S5000, when the first image data is a vehicle image, the processing module generates a recognition result according to the first image data. Among them, the recognition result includes the license plate recognition result.

In step S2000, the vehicle data of the vehicle at the first position is acquired by the data acquisition device. Among them, the data acquisition device includes a radio frequency sensor device, an infrared sensor device, and so on. The vehicle information contains the registration information of the vehicle. Specifically, in one embodiment, a radio frequency sensing device is used to obtain the vehicle registration data of the radio frequency tag of the vehicle. Among them, the registration information can be the license plate number of the vehicle, or the license plate number can be queried.

In step S4000, the processing module compares whether the recognition result matches the vehicle data. Specifically, in one embodiment, the license plate number of the recognition result is compared with the license plate number of the vehicle data to confirm whether the two match.

In step S6000, when the recognition result matches the vehicle data, the processing module generates a confirmation signal.

Based on the above, in the vehicle identification method of the present invention, because the identification result generated based on the first image data and the vehicle data obtained from the data acquisition device are compared with each other to confirm, instead of directly using one of the two Therefore, it is possible to reduce the chance of problems when using image recognition alone or data reading alone, resulting in an error in the final vehicle recognition result, so it has better accuracy.

In the embodiment shown in FIGS. 1A and 1B, steps S2000, S4000, and S6000 are performed after steps S1000, S3000, and S5000. However, in different embodiments, steps S2000, S4000, and S6000 may be the same as steps S1000, S3000, and S3000. S5000 is performed simultaneously or before it. In the embodiment shown in FIG. 2, steps S2000, S4000, and S6000 are performed synchronously with steps S1000, S3000, and S5000.

As shown in the embodiment shown in FIG. 3, the vehicle identification method of the present invention may further include, for example, the following steps before step S1000.

Step S0511, the first position is sensed by the motion sensing module. Step S0512, when the motion sensing module senses the motion, proceed to step S1000. Among them, the motion sensing module includes a sensing device or computer program that uses optical (such as laser, infrared), sound waves (such as ultrasound), image difference analysis and other principles for motion sensing.

As shown in the embodiment shown in FIG. 4, the vehicle identification system 900 of the present invention includes an image acquisition device 100, a data acquisition device 200, and a processing module 300. The image acquisition device 100 is used to acquire the first image data of the vehicle at the first position. The data acquisition device 200 is used to acquire vehicles in Vehicle information in the first position. The processing module 300 is in communication connection with the image acquisition device 100 and the data acquisition device 200 for distinguishing whether the first image data is a vehicle image and whether the comparison and recognition result matches the vehicle data. When the first image data is a vehicle image, the processing module generates a recognition result according to the first image data. When the comparison result between the first image data and the vehicle profile data is consistent, the processing module determines that the first image data is a vehicle image.

As shown in the embodiment shown in FIG. 5, the vehicle identification system 900 of the present invention further includes a motion sensing module 400 in communication connection with the processing module for motion sensing of the first position.

One of the characteristics of the present invention based on the above is to compare the recognition result generated from the image data and the data obtained from the data acquisition device for confirmation, instead of directly using one of the two, so it can reduce the use of image recognition alone. Or a problem occurs when the data is read alone, which leads to a chance of obtaining an incorrect recognition result. Based on the same broad invention concept, the present invention provides an object recognition method and system.

As shown in the embodiment shown in FIG. 6A, the object recognition method of the present invention includes, for example, the following steps.

Step T1000: Obtain the first image data of the object at the first position by the image acquisition device. Specifically, a digital camera is used as the image acquisition device, and the object is photographed as the first image data. In different embodiments, a digital camera may also be used to record an object, and then a screen capture of the object in the recorded screen is used as the first image data. In one embodiment, the object may be a mechanical part, the first position is a position on the storage conveyor belt, and the image acquisition device is set at the first position to obtain the first image data passing through the position for use as a record of the mechanical parts entering and leaving the storage. one.

In step T3000, the processing module generates a category recognition result according to the first image data. Specifically, the processing module contains data processing functions, which can be, for example, directly installed in the chipset of the image acquisition device or connected with the image acquisition device through the Internet, wired telephone, mobile phone, data cable, microwave, radio, etc. The computer or server to which the communication is connected. Among them, the communication connection generally refers to the connection that can achieve signal transmission through the Internet, wired phones, mobile phones, data cables, microwaves, and radio. The first image data can be sent to the processing module by the image acquisition device. Furthermore, the processing module uses artificial intelligence to perform various condition judgments to generate a category recognition result based on the first image data.

Furthermore, as shown in FIG. 6B, in one embodiment, step T3000 includes the following steps.

In step T3100, the processing module compares the first image data with the category contour data. In step T3300, when the comparison result of the first image data and the object outline data in the category outline data matches, the processing module generates the category recognition result.

Among them, the object outline data generally refers to the general outline of the object appearance. The object outline data can be pre-stored in the processing module, or stored in an external storage medium for the processing module to connect and read. The so-called match between the first image data and the object outline data includes that the first image data and the object outline data have the same characteristics.

In step T2000, the data acquisition device acquires the object data of the object at the first position, where the object data includes category data.

In step T4000, the processing module compares whether the category recognition result matches the category data.

In step T6000, when the category identification result matches the category data, the processing module generates a confirmation signal.

Continuing the embodiment in which the object is a mechanical part and the first position is the position on the storage conveyor belt, the first image data acquired by the image acquisition device is the image of the steering wheel object, which is different from the object contour data of the "steering wheel" in the category contour data. If the comparison results match, the processing module will generate a "steering wheel" category recognition result. The category data of the object data obtained by the data acquisition device of the steering wheel object at the first position is also "steering wheel". The processing module compares the two and generates a confirmation signal. Thereby, it can be confirmed that the objects entering and leaving the storage through the first position are the steering wheel.

Unmanned storage management is the future trend, and the use of wireless tags or image recognition for object identification to record and manage the entry and exit of objects in the storage is one of the important technologies. According to the above, in the object recognition method of the present invention, the recognition result generated based on the first image data and the object data obtained from the data acquisition device are compared to confirm each other, instead of directly using one of the two Therefore, it is possible to reduce the chance of problems when using image recognition alone or data reading alone, resulting in an error in the final object recognition result, so it has better accuracy.

In the foregoing embodiment shown in FIGS. 6A and 6B, steps T2000, T4000, and T6000 are performed after steps T1000, T3000, and T5000. However, in different embodiments, steps T2000, T4000 and T6000 can be performed simultaneously with or before steps T1000, T3000, and T5000. In the embodiment shown in Fig. 7, steps T2000, T4000, and T60000 are performed synchronously with steps T1000, T3000, and T5000.

As shown in the embodiment shown in FIG. 8, the object recognition method of the present invention may further include, for example, the following steps before step T1000.

Step T0511, the first position is sensed by the motion sensing module. Step T0512, when the motion sensing module senses the motion, proceed to step T1000. Among them, the motion sensing module includes a sensing device or computer program that uses optical (such as laser, infrared), sound waves (such as ultrasound), image difference analysis and other principles for motion sensing.

As shown in the embodiment shown in FIG. 9, the object recognition system 910 of the present invention includes an image acquisition device 110, a data acquisition device 210, and a processing module 310. The image acquisition device 110 is used to acquire the first image data of the object at the first position. The data acquisition device 210 is used to acquire the object data of the object at the first position, where the object data includes category data. The processing module 310 is in communication with the image acquisition device 210 and the data acquisition device 310 for generating a category recognition result based on the first image data and comparing whether the category recognition result matches the category data. When the category recognition result matches the category data, the processing module generates a confirmation signal.

As shown in the embodiment shown in FIG. 10, the object recognition system 910 of the present invention further includes a motion sensing module 410 in communication with the processing module for motion sensing of the first position.

Although the foregoing description and drawings have disclosed the preferred embodiment of the present invention, it must be understood that various additions, many modifications and substitutions may be used in the preferred embodiment of the present invention without departing from the scope of the attached patent application. The spirit and scope of the principles of the present invention. Those skilled in the art familiar with the technical field of the present invention will appreciate that the present invention can be used in many forms, structures, arrangements, proportions, materials, elements, and component modifications. Therefore, the embodiments disclosed herein should be considered to illustrate the present invention, rather than to limit the present invention. The scope of the present invention should be defined by the scope of the attached patent application, and cover its legal equivalents, and is not limited to the previous description.

S1000‧‧‧Step

S2000‧‧‧Step

S3100‧‧‧Step

S3300‧‧‧Step

S4000‧‧‧Step

S5000‧‧‧Step

S6000‧‧‧Step

Claims (10)

A vehicle identification method includes the following steps: (S1000) Obtain a first image data of a vehicle at a first position by an image acquisition device; (S3000) Determine whether the first image data is a vehicle image by a processing module (S5000) When the first image data is a vehicle image, the processing module generates a recognition result based on the first image data; (S2000) A data acquisition device acquires a vehicle data of the vehicle at the first position (S4000) The processing module compares whether the recognition result matches the vehicle data; (S6000) when the recognition result matches the vehicle data, the processing module generates a confirmation signal. The vehicle identification method according to claim 1, wherein the step (S3000) includes the following steps: (S3100) comparing the first image data with a vehicle profile data by the processing module; (S3300) when the first The image data matches the comparison result of the vehicle profile data, and the processing module determines that the first image data is a vehicle image. The vehicle identification method according to claim 1, further comprising the following steps before step (S1000): (S0511) sensing the first position by a motion sensing module; (S0512) when the motion sensing module The group senses an action and proceeds to this step (S1000). A vehicle identification system using the vehicle identification method according to any one of claims 1 to 3, comprising: an image acquisition device for acquiring first image data of a vehicle at a first position; and a data acquisition device for Acquiring vehicle data of the vehicle at the first position; A processing module is communicatively connected with the image acquisition device and the data acquisition device for distinguishing whether the first image data is a vehicle image. When the first image data is a vehicle image, the processing module is A recognition result is generated from the image data; and whether the recognition result is consistent with the vehicle data, and when the comparison result of the first image data matches the vehicle profile data, the processing module determines that the first image data is a vehicle image. The vehicle identification system according to claim 4, further comprising a motion sensing module communicating with the processing module for motion sensing on the first position. An object recognition method, including the following steps: (T1000) Obtain a first image data of an object at a first location by an image acquisition device; (T3000) Generate a category identification based on the first image data by a processing module Result; (T2000) Obtain the object data of the object at the first location by a data acquisition device, where the object data includes a category data; (T4000) Compare the category recognition result with the category data by the processing module Whether it matches; (T6000) When the recognition result of the category matches the data of the category, the processing module generates a confirmation signal. The object identification method according to claim 6, wherein the step (T3000) includes the following steps: (T3100) compare the first image data with a category profile data by the processing module; (T3300) when the first The comparison result between the image data and the contour data of an object in the category contour data is consistent, and the processing module generates the recognition result of the category. The object identification method described in claim 6, further includes the following steps before step (T1000) Step: (T0511) Sensing the first position by a motion sensing module; (T0512) When the motion sensing module senses a motion, perform this step (T1000). An object recognition system using the object recognition method according to any one of claims 6 to 8, comprising: an image acquisition device for acquiring first image data of an object at a first location; and a data acquisition device for Obtain the object data of the object at the first location, where the object data includes a category data; a processing module, which is communicatively connected with the image acquisition device and the data acquisition device, for: generating a data based on the first image data Category recognition result; and compare whether the category recognition result matches the category data, and when the category recognition result matches the category data, the processing module generates a confirmation signal. The object recognition system according to claim 9, further comprising a motion sensing module in communication with the processing module for motion sensing on the first position.

Images